Frontier coding agents surpass published Nature-family SOTA on only 17.8% of 90 sealed scientific tasks, mostly by recasting problems as supervised ML rather than inventing methods.
hub
Pan, Alexander Du, Kurt Keutzer, Alvin Cheung, Alexandros G
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 22roles
background 3polarities
background 3representative citing papers
FAPO automates LLM pipeline optimization via iterative diagnosis and prompt-or-structure edits, beating GEPA baseline by +14.1 pp mean across 18 comparisons and +33.8 pp when structural changes occur.
MotionDisco discovers long-horizon humanoid loco-manipulation motions from scratch via LLM-guided evolutionary search, trajectory optimization, and pruning, then transfers them to real robots with RL policies.
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
DIO-Agent frames IO2Code as LLM-driven evolutionary search over programs with a Transformation Priority Premise to favor simple hypotheses, outperforming baselines on a new IO2CodeBench.
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
AlphaEvolve automates optimization of TFHE and CKKS FHE kernels on TPUv5e, finding changes that cut bootstrap latency by 2.5x and rotation/multiplication by 1.31x/1.18x versus human baselines.
FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.
CoupleEvo finds that sequential and iterative strategies for evolving LLM-based heuristics yield more stable and higher-quality solutions than an integrated strategy on coupled optimization problems.
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
Evolution Fine-Tuning trains LLMs on 156K trajectories spanning 371 tasks to achieve 10.22% average improvement on 22 held-out optimization tasks and match SOTA on select circle-packing problems when combined with test-time RL.
CHIA is a distributed graph-based framework for composing, deploying, and verifying agentic AI hardware/software co-design flows, demonstrated on RTL, simulation, and compiler tasks.
AIChilles finds 49 distinct hidden weaknesses across 30 AI-evolved programs in five applications by combining workload extraction, agent-based constraint inference, differential oracles, and coverage to expose regressions.
EvoDrive presents an LLM-based agentic evolution framework that generates diverse safety-critical autonomous driving scenarios by maintaining a Pareto archive of attack-realism trade-offs using simulator feedback.
BenchEvolver evolves coding problem solutions to generate harder, valid tasks, producing LiveCodeBench-Plus where frontier models score 27.5-62.6% and enabling RL gains on held-out tests.
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
A dual-population evolutionary ensemble of coding agents discovers a rescale-then-interpolate PE for ICON example-count generalization and outperforms static-agent baselines via stage-dependent adaptation.
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
EEVEE introduces a router-based multi-dataset test-time prompt learning framework for LLM agents that uses router-prompt co-evolution to improve robustness on heterogeneous data streams.
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.
citing papers explorer
-
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Frontier coding agents surpass published Nature-family SOTA on only 17.8% of 90 sealed scientific tasks, mostly by recasting problems as supervised ML rather than inventing methods.
-
FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
FAPO automates LLM pipeline optimization via iterative diagnosis and prompt-or-structure edits, beating GEPA baseline by +14.1 pp mean across 18 comparisons and +33.8 pp when structural changes occur.
-
MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
MotionDisco discovers long-horizon humanoid loco-manipulation motions from scratch via LLM-guided evolutionary search, trajectory optimization, and pruning, then transfers them to real robots with RL policies.
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
From I/O to Code with Discovery Agent
DIO-Agent frames IO2Code as LLM-driven evolutionary search over programs with a Transformation Priority Premise to favor simple hypotheses, outperforming baselines on a new IO2CodeBench.
-
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
-
Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUs
AlphaEvolve automates optimization of TFHE and CKKS FHE kernels on TPUv5e, finding changes that cut bootstrap latency by 2.5x and rotation/multiplication by 1.31x/1.18x versus human baselines.
-
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.
-
CoupleEvo: Evolving Heuristics for Coupled Optimization Problems Using Large Language Models
CoupleEvo finds that sequential and iterative strategies for evolving LLM-based heuristics yield more stable and higher-quality solutions than an integrated strategy on coupled optimization problems.
-
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
-
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Evolution Fine-Tuning trains LLMs on 156K trajectories spanning 371 tasks to achieve 10.22% average improvement on 22 held-out optimization tasks and match SOTA on select circle-packing problems when combined with test-time RL.
-
CHIA: An open-source framework for principled, agentic AI-driven hardware/software co-design research
CHIA is a distributed graph-based framework for composing, deploying, and verifying agentic AI hardware/software co-design flows, demonstrated on RTL, simulation, and compiler tasks.
-
AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems
AIChilles finds 49 distinct hidden weaknesses across 30 AI-evolved programs in five applications by combining workload extraction, agent-based constraint inference, differential oracles, and coverage to expose regressions.
-
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
EvoDrive presents an LLM-based agentic evolution framework that generates diverse safety-critical autonomous driving scenarios by maintaining a Pareto archive of attack-realism trade-offs using simulator feedback.
-
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
BenchEvolver evolves coding problem solutions to generate harder, valid tasks, producing LiveCodeBench-Plus where frontier models score 27.5-62.6% and enabling RL gains on held-out tests.
-
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
-
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
-
Evolutionary Ensemble of Agents
A dual-population evolutionary ensemble of coding agents discovers a rescale-then-interpolate PE for ICON example-count generalization and outperforms static-agent baselines via stage-dependent adaptation.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents
EEVEE introduces a router-based multi-dataset test-time prompt learning framework for LLM agents that uses router-prompt co-evolution to improve robustness on heterogeneous data streams.
-
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
-
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.